Scaling Diffusion Models to Real-World 3D LiDAR Scene Completion

arXiv:2403.13470v1 Announce Type: new
Abstract: Computer vision techniques play a central role in the perception stack of autonomous vehicles. Such methods are employed to perceive the vehicle surroundings given sensor data. 3D LiDAR sensors are commonly used to collect sparse 3D point clouds from the scene. However, compared to human perception, such systems struggle to deduce the unseen parts of the scene given those sparse point clouds. In this matter, the scene completion task aims at predicting the gaps in …

abstract arxiv autonomous autonomous vehicles computer computer vision cs.cv data diffusion diffusion models however human lidar perception role scaling sensor sensors stack type vehicles vision world